publication . Other literature type . Article . 2010

Object Detection with Discriminatively Trained Part-Based Models

P F Felzenszwalb; R B Girshick; D McAllester; D Ramanan;
  • Published: 01 Sep 2010
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Abstract
We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges. While deformable part models have become quite popular, their value had not been demonstrated on difficult benchmarks such as the PASCAL data sets. Our system relies on new methods for discriminative training with partially labeled data. We combine a margin-sensitive approach for data-mining hard negative examples with a formalism we call latent SVM. A latent SVM is a reformulation of MI--SVM in terms of latent variables. A lat...
Subjects
arXiv: Statistics::Machine LearningComputer Science::Machine Learning
ACM Computing Classification System: ComputingMethodologies_PATTERNRECOGNITION
free text keywords: General Computer Science, Object visualization, Bright light, Clothing, business.industry, business, Image detection, Pattern recognition, Computer vision, Object detection, Computer science, Shadow, Computer security, computer.software_genre, computer, Artificial intelligence, Viola–Jones object detection framework, Machine learning, Linear discriminant analysis, Latent variable, Discriminative model, Cognitive neuroscience of visual object recognition, Support vector machine, Probabilistic latent semantic analysis
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue